Abstract
We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently.
Abstract (translated)
我们考虑一个新的问题解答（QA）任务，机器需要在不知道何时给出问题的情况下从大型流数据（长文档或视频）中读取数据，在这种情况下，现有的QA方法由于缺乏可扩展性而失败。为了解决这个问题，我们提出了一种新的端到端阅读理解方法，我们称之为情景式记忆阅读器（EMR），它将输入上下文按顺序读取到外部记忆中，同时替换那些对于回答看不见的问题不太重要的记忆。具体地说，我们训练一个RL代理在内存满时替换一个内存条目，以便在将来的时间点最大限度地提高其QA准确性，同时使用Transformer体系结构对外部内存进行编码，以学习考虑到内存条目之间相对重要性的表示。我们在一个真实的大规模文本质量保证任务（triviaqa）和一个视频质量保证任务（tvqa）上验证了我们的模型，在这个模型上，它比基于规则的内存调度策略或基于RL的基线（它们独立地学习每个内存的特定查询重要性）有了显著的改进。
URL
https://arxiv.org/abs/1903.06164
